get_mitre_techniques
AI agents call get_mitre_techniques to retrieve information from Wazuh MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite empty description, the 'get_' prefix and context as part of a security monitoring platform strongly suggest this retrieves reference data about MITRE ATT&CK techniques without modifying or executing anything. This is consistent with Read category tools used for security analysis.
From the tool's definition Tool name 'get_mitre_techniques' and sibling tools on the Wazuh MCP Server (all prefixed with 'get_' or 'count_') indicate read-only data retrieval. The tool appears to fetch MITRE ATT&CK technique information for security analysis purposes.
Attacks that exploit this kind of access
get_mitre_techniques. It is categorised as a Read tool in the Wazuh MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Wazuh MCP Server MCP server in PolicyLayer and add a rule for get_mitre_techniques: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Wazuh MCP Server. Nothing to install.
get_mitre_techniques is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_mitre_techniques rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_mitre_techniques. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_mitre_techniques is provided by the Wazuh MCP Server MCP server (rayasatriatama/wazuh-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →